Grok 4.6
xAI · released Aug 12, 2026
- Type
- Closed
- Input
- $2.00
- Output
- $6.00
- Cached
- None held
List price · per 1M tokens · xAI at 500K context · machine-readable source ↗
Our take
Written Sep 17, 2026Grok 4.6 is a hosted-only model from xAI, so using it means choosing a host rather than running it yourself. Its measured strengths sit in mathematics and reasoning, while its agentic task-outcome score falls below the board's neutral point.
Reach for it on mathematical and reasoning-heavy work, where its measured scores are strongest, or for long-document analysis where the request capacity spares you from splitting files first. It also takes images and files alongside text. Skip it if you need to run the model yourself or need clear licence terms, or if you need an agent that reliably finishes multi-step tasks.
The case for it
- Among the strongest on LiveBench Mathematics and Reasoning, at 92.57% and 90.51% — averages over competition-style and monthly-refreshed task sets.
- The request capacity is large enough that long documents need not be split up first, though reliable recall across all of it is unverified in our data.
- Text, images and files go into the same request, so a screenshot or a document does not have to be transcribed first.
The case against it
- Arena Agent task outcome is negative, meaning it finished the session's task less often than the board's neutral point, while recovery, steerability and tool use are positive but small.
- We list no download for it, so using it means choosing a host, and no licence terms are disclosed in our data.
- Agentic coding is much weaker than its other coding measures: 57.02% on LiveBench Agentic Coding, measured inside an agent harness, against 76.78% on LiveBench Coding.
How good is it?
A closed text model from xAI for drafting prose, writing code and calling tools to carry out requests.
- drafts, rewrites and editingArena Creative Writing · 33rd of 168
- writing and completing codeArena Coding · 41st of 168
- calling tools to carry out requestsArena Agent · Tool use · 9th of 55
EverydayGeneral questions and everyday reasoning
Arena Text (overall)47th of 168 · 1453
CodingWriting and fixing code on its own
Arena Coding41st of 168 · 1507
AgenticPlanning, calling tools, staying on task
Arena Agent23rd of 55 · 0.012
WritingDrafting and rewriting prose
Arena Creative Writing33rd of 168 · 1445
Placings on Arena's agent boards, from live sessions people ran themselves. A model can lead on one of these and sit mid-field on the others.
Boards this model appears on that none of the ratings above are built on.
Every published score for this model20 scoresEvery figure we hold, from 20 boards, with who ran it and a link to the source — including the boards no rating above is built on.
Where to rent it
Prices checked between 58 min and 1 hour ago — each listing carries its own date.
xAI, direct and through OpenRouter
The lab is also the cheapest we hold. The strip above and this offer are the same one, so nothing on this page undercuts xAI on 500K of context.
- per 1M tokens
- $2.00 in / $6.00 out
- Context served
- 500K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $2.00 / $6.00checked 1 hour ago | 500K | not measured | Unknown | Unknown | Unknown |
| xAIDirect and through OpenRouter | $2.00 / $6.00checked 58 min ago directchecked 59 min ago through OpenRouter | 500K500K max reply direct450K max reply through OpenRouter | 53 tok/sthrough OpenRouter | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterYes30 days | DirectUnknownThrough OpenRouterConfirmed |
| xAIusThrough OpenRouter | $2.20 / $6.60checked 59 min ago | 500K450K max reply | 50 tok/s | No | Yes30 days | Confirmed |
| Amazon Bedrockus-west-2Through OpenRouter | $2.20 / $6.60checked 59 min ago | 500K450K max reply | 94 tok/s | No | No | Confirmed |
| xAIpriority tierThrough OpenRouter | $4.00 / $12.00checked 59 min ago | 500K450K max reply | 70 tok/s | No | Yes30 days | Confirmed |
OpenRouter
Amazon BedrockAcross the 5 listings we hold: 4 say they do not train on prompts (1 of them only through OpenRouter), 0 say they do and 1 does not say. 4 appear in the zero-retention registry we check (1 of them only through OpenRouter); the rest are unknown to us.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouterOpenRouter's own listing | ✓ | ✓ | ✓ |
| xAIDirect and through OpenRouter | ✓ | ✓ | ✓ |
| xAIusThrough OpenRouter | ✓ | ✓ | ✓ |
| Amazon Bedrockus-west-2Through OpenRouter | ✓ | ✓ | ✓ |
| xAIpriorityThrough OpenRouter | ✓ | ✓ | ✓ |
Tool calling: 5 of 5 listings say yes. JSON output: 5 of 5 listings say yes. Strict schema: 5 of 5 listings say yes.
Models people weigh against Grok 4.6
When we formed this view
Recent changes
Each date is the day we first saw the change, or the day the maker announced it.
What we do not know about this model yet
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 5 listings does not say whether it trains on prompts, and 1 answers only through OpenRouter, not for its own listing.
- We hold no batch or off-peak rate for any of its listings.
Licence and identifiers
What the licence allowsWe hold no licence record for this model. Inside are the identifiers you need to pull it — its Hugging Face repo where we have one, our slug and a machine-readable card.
Licence
We hold no licence record for this model, and no record of published weights either — so we can neither summarise its terms nor point you at the weights.
Identifiers
- Takes in, gives back
- Text, images and documents in, text out
- Catalogue slug
- x-ai-grok-4-6